Financial institutions are required to absorb risks associated with foreign exchange (FX) transactions. In this talk, preliminary work in applying machine learning to better understand and manage such exposure will be presented, in particular (1) a technique to efficiently cluster non-periodic time series, (2) use of grammars to generate features based on technical indicators, (3) an SVM-based customer flow prediction engine, and (4) hedging strategies under the Markowitz framework.
Philip Leong received the B.Sc., B.E. and Ph.D. degrees from the University of Sydney. In 1993 he was a consultant to ST Microelectronics in Milan, Italy working on advanced flash memory-based integrated circuit design. From 1997-2009 he was with the Chinese University of Hong Kong. He is currently an Associate Professor in the School of Electrical and Information Engineering at the University of Sydney, a Visiting Professor at Imperial College, London and the Chief Technology Advisor to Cluster Technology.